← Search

Dylan Paiton

2 accepted papers

2021

Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding

ICLR 2021oral

Disentangling the underlying generative factors from complex data has so far been limited to carefully constructed scenarios. We propose a path towards natural data by first showing that the statistics of natural data provide enough structure to enable disentanglement, both theoretically and empiric…